Refined Color Texture Classification Using CNN and Local Binary Pattern

Representation and classification of color texture generate considerable interest within the field of computer vision. Texture classification is a difficult task that assigns unlabeled images or textures to the correct labeled class. Some key factors such as scaling and viewpoint variations and illumination changes make this task challenging. In this paper, we present a new feature extraction technique for color texture classification and recognition. The presented approach aggregates the features extracted from local binary patterns (LBP) and convolution neural network (CNN) to provide discriminatory information, leading to better texture classification results. Almost all of the CNN model cases classify images based on global features that describe the image as a whole to generalize the entire object. LBP classifies images based on local features that describe the image’s key points (image patches). Our analysis shows that using LBP improves the classification task when compared to using CNN only. We test the proposed approach experimentally over three challenging color image datasets (ALOT, CBT, and Outex). The results demonstrated that our approach improved up to 25% in the classification accuracy over the traditional CNN models. We identify optimal combinations for each dataset and obtain high classification rates. The proposed approach is robust, stable, and discriminatory among the three datasets and has shown enhancement in classification and recognition compared to the state-of-the-art method.

Structural connectivity differs between males and females in the brain object manipulation network

Object control skills are one of the most important abilities in daily life. Knowledge of object manipulation is an essential factor in improving object control skills. Although males and females equally try to use object manipulation knowledge, their object control abilities often differ. To explain this difference, we investigated how structural brain networks in males and females are differentially organized in the tool-preferring areas of the object manipulation network. The structural connectivity between the primary motor and premotor regions and between the inferior parietal regions in males was significantly higher than that in females. However, females showed greater structural connectivity in various regions of the object manipulation network, including the paracentral lobule, inferior parietal regions, superior parietal cortices, MT+ complex and neighboring visual areas, and dorsal stream visual cortex. The global node strength found in the female parietal network was significantly higher than that in males but not for the entire object manipulation, ventral temporal, and motor networks. These findings indicated that the parietal network in females has greater inter-regional structural connectivity to retrieve manipulation knowledge than that in males. This study suggests that differential structural networks in males and females might influence object manipulation knowledge retrieval.

A Method to Reduce Air Heating Costs in Winter Period in the Królowa Luiza Mining Museum in Zabrze – Case Study

The Królowa Luiza Mining Museum is one of the touristic objects of the Coal Mining Museum in Zabrze. In the study in concern, an assessment of ventilation of the facility was conducted. Following the assessment of the ventilation, the operating parameters of the fans were changed, inlets were sealed and a system of air ducts was designed and constructed. The ducts reintroduce the heated air from the facility to workings. The conducted activities aimed to decrease the amount of air has increased the temperature in the entire object by from 3 to 10°C, which translated into a profit of approximately 200 Euro a day. Before changing the heating system it was impossible to achieve a positive temperature in the entire object at an external temperature of −10°C. It was necessary to close the Museum for tourists. Trials conducted for the external temperature from −2 to −6°C have exhibited that it will be possible to achieve positive temperatures in the entire facility even in case of very low external temperatures. The costs borne for the change of the heating system may be estimated at a level of 25000 Euro. The return of the investment should occur in the first Winter period.

An Improved Approach for Object Proposals Generation

The objectness measure is a significant and effective method used for generic object detection. However, several object detection methods can achieve accurate results by using more than 1000 candidate object proposals. In addition, the weight of each proposal is weak and also cannot distinguish object proposals. These weak proposals have brought difficulties to the subsequent analysis. To significantly reduce the number of proposals, this paper presents an improved generic object detection approach, which predicts candidate object proposals from more than 10,000 proposals. All candidate proposals can be divided, rather than preclassified, into three categories: entire object, partial object, and nonobject. These partial object proposals also display fragmentary information of the objectness feature, which can be used to reconstruct the object boundary. By using partial objectness to enhance the weight of the entire object proposals, we removed a huge number of useless proposals and reduced the space occupied by the true positive object proposals. We designed a neural network with lightweight computation to cluster the most possible object proposals with rerank and box regression. Through joint training, the lightweight network can share the features with other subsequent tasks. The proposed method was validated using experiments with the PASCAL VOC2007 dataset. The results showed that the proposed approach was significantly improved compared with the existing methods and can accurately detect 92.3% of the objects by using less than 200 proposals.

Review of Introduction To Property Testing by Oded Goldreich

The area of property testing is concerned with designing methods to decide whether an input object possesses a certain property or not. Usually the problem is described as a promise problem: either the input object has the property or the input object is far from possessing the property. Here, the meaning of object being far from possessing the property is based on a specified and meaningful notion of distance. The main objective of property testing is accomplishing this decision making by developing a super efficient tester. A tester that reads through the entire object can easily determine whether the property is satisfied or not. However, one wishes the tester to probe the input at very few random locations and determine whether the property is satisfied. As such, randomness is a necessary ingredient for testing and having the tester erring on few instances is a necessary price to pay for designing highly efficient methodologies. Much of the literature on property testing has focused on two types of objects: functions and graphs. Naturally they form the major portion of the book: functions are discussed from Chapters 2 to 6 and graph properties are discussed from Chapters 8 to 10. The final three chapters focus on distribution testing, probabilistically checkable proofs (PCPs) and locally testable codes, and ramifications of property testing on other related topics in Computer Science and Statistics. A separate chapter is devoted to query lower bound techniques.

Magnetic resonance microscopy of samples with translational symmetry with FOVs smaller than sample size

In MRI, usually the Field of View (FOV) has to cover the entire object. If this condition is not fulfilled, an infolding image artifact is observed, which suppresses visualization. In this study it is shown that for samples with translational symmetry, i.e., those consisting of identical objects in periodic unit cells, the FOV can be reduced to match the unit cell which enables imaging of an average object, of which the signal is originated from all unit cells of the sample, with no punishment by a loss in signal-to-noise ratio (SNR). This theoretical prediction was confirmed by experiments on a test sample with a 7 × 7 mm2 unit cell arranged in a 3 × 3 matrix which was scanned by the spin-echo and by single point imaging methods. Effects of experimental imperfections in size and orientation mismatch between FOV and unit cell were studied as well. Finally, this method was demonstrated on a 3D periodic sample of tablets, which yielded well-resolved images of moisture distribution in an average tablet, while single tablet imaging provided no results. The method can be applied for SNR increase in imaging of any objects with inherently low signals provided they can be arranged in a periodic structure.

The Influence of the Cuboid Float’s Parameters on the Stability of a Floating Building

Usually, the concept of sufficient stability of a floating structure is connected with the capacity to keep a small heel angle despite the moment of heeling. The variable responsible for these characteristics is the initial metacentric height, which is the relation between the hydrostatic features of the pontoon and the mass properties of the entire object. This article answers the questions of how heavy the floating system should be, what the minimum acceptable draft is, and whether it is beneficial to use internal fixed ballast. To cover various technologies, a theoretical model of a cuboid float with average density representing different construction materials was analysed. The results indicate that the common practice of using heavy and deep floating systems is not always reasonable. In the case of floating buildings, which, unlike ships, can be exploited only under small heel angles, the shape and width of the submerged part of the object may influence the stability more than the weight or draft.

SEMANTICS OF SPACE IN THE RIDDLES OF KOMI PEOPLE: DWELLING

Semantics of space is one of the topical topics of modern research. As an essential part of the mythopoietic picture of the world, space often relates to the home/dwelling image. The image of the house and it’s repositions in various folklore genres, rites and traditions were addressed by many researchers. In particular, house/dwelling - as one of the fundamental semanthems in the folklore model of the world is considered by T. V. Civyan on the example of Balkan riddles. Based on this and other research, we will show how the image of the house is realized in the riddles of the people of Komi. The material of the study was the published and unpublished texts of Komi riddles from linguistic collections and archival sources of the mid-19th - the first third of the 20th centuries. Analysis of the texts showed that the house, its elements and related objects form an essential part of the entire body of riddles. The house as an entire object, but more often - at the level of its constituent components - appears both in the part to be enunciated and guessed (denotative), in a large number of texts. The set of these components is in principle universal for most traditions to ask riddles, including for Komi.

Filtration and Distillation: Enhancing Region Attention for Fine-Grained Visual Categorization

Delicate attention of the discriminative regions plays a critical role in Fine-Grained Visual Categorization (FGVC). Unfortunately, most of the existing attention models perform poorly in FGVC, due to the pivotal limitations in discriminative regions proposing and region-based feature learning. 1) The discriminative regions are predominantly located based on the filter responses over the images, which can not be directly optimized with a performance metric. 2) Existing methods train the region-based feature extractor as a one-hot classification task individually, while neglecting the knowledge from the entire object. To address the above issues, in this paper, we propose a novel “Filtration and Distillation Learning” (FDL) model to enhance the region attention of discriminate parts for FGVC. Firstly, a Filtration Learning (FL) method is put forward for discriminative part regions proposing based on the matchability between proposing and predicting. Specifically, we utilize the proposing-predicting matchability as the performance metric of Region Proposal Network (RPN), thus enable a direct optimization of RPN to filtrate most discriminative regions. Go in detail, the object-based feature learning and region-based feature learning are formulated as “teacher” and “student”, which can furnish better supervision for region-based feature learning. Accordingly, our FDL can enhance the region attention effectively, and the overall framework can be trained end-to-end without neither object nor parts annotations. Extensive experiments verify that FDL yields state-of-the-art performance under the same backbone with the most competitive approaches on several FGVC tasks.